© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36590
    Prev
    Next
    INDEX
    Explanations

    physical world

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_11_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,}
    0.57
    ,[
    0.55
    izante
    0.54
    所に
    0.54
    ER
    0.52
    ,
    0.52
     be
    0.52
    ((
    0.51
    ăți
    0.51
     from
    0.50
    POSITIVE LOGITS
    се
    0.57
     Ereign
    0.57
    λυ
    0.55
    silyl
    0.54
    淍
    0.54
    weise
    0.51
    াদশ
    0.50
    氳
    0.50
    দান
    0.49
    פע
    0.49
    Activations Density 0.003%

    No Known Activations